An Extrinsic Sensor Calibration Framework for Sensor-fusion based Autonomous Vehicle Perception

In this paper we deal with sensor alignment problems that appear when implementing sensor fusion-based autonomous vehicle perception. We focus on extrinsic calibration of vision-based and line scan LIDAR sensors. Based on state-of-art solutions, a consistent calibration toolchain is developed, with improvements (accuracy and calibration duration). Additionally, sensor alignment/calibration impact on fusion-based perception is investigated. Experimental results are provided for illustration, using real-world data.

[1]  Markus Lienkamp,et al.  Improving lidar data evaluation for object detection and tracking using a priori knowledge and sensorfusion , 2014, 2014 11th International Conference on Informatics in Control, Automation and Robotics (ICINCO).

[2]  Kyungeun Cho,et al.  Calibration between Color Camera and 3D LIDAR Instruments with a Polygonal Planar Board , 2014, Sensors.

[3]  Vincent Frémont,et al.  Circular Targets for 3D Alignment of Video and Lidar Sensors , 2012, Adv. Robotics.

[4]  Rui P. Rocha,et al.  Data Fusion Calibration for a 3D Laser Range Finder and a Camera using Inertial Data , 2009, ECMR.

[5]  Zhidong Deng,et al.  A new algorithm for the establishing data association between a camera and a 2-D LIDAR , 2014, Tsinghua Science and Technology.

[6]  Zheng Liu,et al.  Automatic calibration and registration of lidar and stereo camera without calibration objects , 2015, 2015 IEEE International Conference on Vehicular Electronics and Safety (ICVES).

[7]  Thierry Fraichard,et al.  Fusion between laser and stereo vision data for moving objects tracking in intersection like scenario , 2011, 2011 IEEE Intelligent Vehicles Symposium (IV).

[8]  Cindy Cappelle,et al.  Optimal Extrinsic Calibration Between a Stereoscopic System and a LIDAR , 2013, IEEE Transactions on Instrumentation and Measurement.

[9]  N. Trawny,et al.  Indirect Kalman Filter for 3 D Attitude Estimation , 2005 .

[10]  Stergios I. Roumeliotis,et al.  An analytical least-squares solution to the line scan LIDAR-camera extrinsic calibration problem , 2013, 2013 IEEE International Conference on Robotics and Automation.